A Discriminative Approach to Grounded Spoken Language Understanding in Interactive Robotics
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2747-2752.
Abstract
Spoken Language Understanding in Interactive Robotics provides computational models of human-machine communication based on the vocal input. However, robots operate in specific environments and the correct interpretation of the spoken sentences depends on the physical, cognitive and linguistic aspects triggered by the operational environment. Grounded language pro- cessing should exploit both the physical constraints of the context as well as knowledge assumptions of the robot. These include the subjective perception of the environment that explicitly affects linguistic reasoning. In this work, a standard linguistic pipeline for semantic parsing is extended toward a form of perceptually informed natural language processing that combines discriminative learning and distributional semantics. Empirical results achieve up to a 40% of relative error reduction.
@inproceedings{ijcai2016p390,
title = {A Discriminative Approach to Grounded Spoken Language Understanding in Interactive Robotics},
author = {Bastianelli, Emanuele and Croce, Danilo and Vanzo, Andrea and Basili, Roberto and Nardi, Daniele},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {2747--2752},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/390},
}
TY - CPAPER TI - A Discriminative Approach to Grounded Spoken Language Understanding in Interactive Robotics AU - Bastianelli, Emanuele AU - Croce, Danilo AU - Vanzo, Andrea AU - Basili, Roberto AU - Nardi, Daniele T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 2747 EP - 2752 UR - https://ijcai.org/proceedings/2016/390 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: